Object shape recognition approach for sparse point clouds from tactile exploration

Jin, Minghe; Gu, Haiwei; Fan, Shaowei; Zhang, Yuanfei; Liu, Hong

doi:10.1109/robio.2013.6739518

Cited by 12 publications

(10 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This allowed the integration of new physical properties that cannot be estimated using vision, such as material [4], compliance [16] and texture [17] for object recognition. Several works have been proposed to deal with challenges associated with tactile data processing, including data sparsity and noise [18], choice of object sets, and the sensing capabilities and constraints of robots [2] and using techniques such as deep learning [1] and sparse coding [19]. Recent advances in tactile object recognition are reviewed in [20].…”

Section: A Multi-class Tactile Recognitionmentioning

confidence: 99%

“…4a) on returning 'synthetic' when inputting f gen and 'real' when inputting f ext (lines [11][12][13][14][15][16]. We keep fine-tuning D until its loss becomes lower than a certain threshold σ D (lines [17][18][19]. Then, we switch to fine-tuning G using the newly trained D and the pre-trained FC FY simultaneously (see Fig.…”

Section: Generating Realistic Featuresmentioning

confidence: 99%

See 1 more Smart Citation

A Deep Learning Framework for Tactile Recognition of Known as Well as Novel Objects

Abderrahmane

Ganesh

Crosnier

et al. 2020

IEEE Trans. Ind. Inf.

View full text Add to dashboard Cite

This paper addresses the recognition of daily-life objects by a robot equipped with tactile sensors. The main contribution is a deep learning framework that can recognize objects already touched as well as objects never touched before. To this end, we train a Deconvolutional Neural Network that generates synthetic tactile data for novel classes. Then, we use both these synthetic data and the real data collected by touching objects, to train a Convolutional Neural Network to recognize both known (trained) objects and novel objects. Furthermore, we propose a method for integrating newly encountered data into novel classes. Finally, we evaluate the framework using the largest available dataset of tactile objects descriptions.

show abstract

Section: A Multi-class Tactile Recognitionmentioning

confidence: 99%

Section: Generating Realistic Featuresmentioning

confidence: 99%

A Deep Learning Framework for Tactile Recognition of Known as Well as Novel Objects

Abderrahmane

Ganesh

Crosnier

et al. 2020

IEEE Trans. Ind. Inf.

View full text Add to dashboard Cite

show abstract

“…After analyzing the tactile information of grasped objects, the least square fitting method and circle fitting method were used to classify and recognize objects. Conversely, Jin et al 27 proposed the Gaussian process classification method for sparse tactile point cloud. Generally, a single grasp can only perceive the shape of the part that is in contact with the tactile sensor, so it can only handle the situation where objects are with simple shapes.…”

Section: Tactile Perception For Shapementioning

confidence: 99%

Recent progress on tactile object recognition

Liu

Sun

et al. 2017

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

Conventional visual perception technology is subject to many restrictions, such as illumination, background clutter, and occlusion. Many intrinsic properties of objects, like stiffness, hardness, and internal state, cannot be effectively perceived by visual sensors. For robots, tactile perception is a key approach to obtain environmental and object information. Different from vision sensors, tactile sensors can directly measure some physical properties of objects and environment. At the same time, humans also utilize touch sensory receptors as an important means to perceive and interact with the environment. In this article, we present a detailed discussion on tactile object recognition problem. We divide the current studies on the tactile object recognition into three subcategories and detailed analysis has been put forward on them. In addition, we also discuss some advanced topics such as visual-tactile fusion, exploratory procedure, and data sets.

show abstract

“…Voxel representations and point-clouds provide a natural way of representing tactile information about objects, but they can be cumbersome in terms of computational power for recognition, as they usually comprise a large number of points/voxels whose matching to a database can be complex, and are prone to noise which is difficult to model. Attempts to address these problems include merging points that are close into a probability point modelled by a Kalman filter [18], and clustering to subdivide the point cloud into regions which are then encoded as features [19].…”

Section: Single Contact Tactile Recognitionmentioning

confidence: 99%

Bayesian tactile object recognition: Learning and recognising objects using a new inexpensive tactile sensor

Corradi

Hall

Iravani

2015

2015 IEEE International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

We present a Bayesian approach to tactile object recognition that improves on state-of-the-art in using singletouch events in two ways. First by improving recognition accuracy from about 90% to about 95%, using about half the number of touches. Second by reducing the number of touches needed for training from about 200 to about 60. In addition, we use a new tactile sensor that is less than one tenth of the cost of widely available sensors. The paper describes the sensor, the likelihood function used with the Naive Bayes classifier, and experiments on a set of ten real objects. We also provide preliminary results to test our approach for its ability to generalise to previously unencountered objects.

show abstract

Object shape recognition approach for sparse point clouds from tactile exploration

Cited by 12 publications

References 16 publications

A Deep Learning Framework for Tactile Recognition of Known as Well as Novel Objects

A Deep Learning Framework for Tactile Recognition of Known as Well as Novel Objects

Recent progress on tactile object recognition

Bayesian tactile object recognition: Learning and recognising objects using a new inexpensive tactile sensor

Contact Info

Product

Resources

About